Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study

Kickingereder, Philipp; Isensee, Fabian; Tursunova, Irada; Petersen, Jens; Neuberger, Ulf; Bonekamp, David; Brugnara, Gianluca; Schell, Marianne; Keßler, Tobias; Foltyn, Martha; Harting, Inga; Sahm, Felix; Prager, Marcel; Nowosielski, Martha; Wick, Antje; Nolden, Marco; Radbruch, Alexander; Debus, Jürgen; Schlemmer, Heinz Peter; Heiland, Sabine; Platten, Michael; Deimling, Andreas von; Bent, Martin J. van den; Gorlia, Thierry; Wick, Wolfgang; Bendszus, Martin; Maier‐Hein, Klaus H.

doi:10.1016/s1470-2045(19)30098-1

Cited by 317 publications

(280 citation statements)

References 70 publications

Supporting

Mentioning

241

Contrasting

Unclassified

Order By: Relevance

“…This signature may be useful for future clinical trials enriched for patients with hypermutated glioblastoma similar to the experimental model used here. Proposed signature might additionally be applied in combination with automated quantitative tumor response assessment of MRI, using artificial networks that will allow for improved clinical decision making 28 . The establishment and application of additional MR protocols to Fig.…”

Section: Discussionmentioning

confidence: 99%

Heterogeneity of response to immune checkpoint blockade in hypermutated experimental gliomas

et al. 2020

Self Cite

View full text Add to dashboard Cite

Intrinsic malignant brain tumors, such as glioblastomas are frequently resistant to immune checkpoint blockade (ICB) with few hypermutated glioblastomas showing response. Modeling patient-individual resistance is challenging due to the lack of predictive biomarkers and limited accessibility of tissue for serial biopsies. Here, we investigate resistance mechanisms to anti-PD-1 and anti-CTLA-4 therapy in syngeneic hypermutated experimental gliomas and show a clear dichotomy and acquired immune heterogeneity in ICB-responder and non-responder tumors. We made use of this dichotomy to establish a radiomic signature predicting tumor regression after pseudoprogression induced by ICB therapy based on serial magnetic resonance imaging. We provide evidence that macrophage-driven ICB resistance is established by CD4 T cell suppression and T reg expansion in the tumor microenvironment via the PD-L1/PD-1/CD80 axis. These findings uncover an unexpected heterogeneity of response to ICB in strictly syngeneic tumors and provide a rationale for targeting PD-L1expressing tumor-associated macrophages to overcome resistance to ICB.

show abstract

Section: Discussionmentioning

confidence: 99%

Heterogeneity of response to immune checkpoint blockade in hypermutated experimental gliomas

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The topology of the ANN underlying the HD-BET algorithm was inspired by the U-Net image segmentation architecture (Ronneberger, Fischer, & Brox, 2015) and its 3D derivatives (Çiçek, Abdulkadir, Lienkamp, Brox, & Ronneberger, 2016;Kayalibay, Jensen, & van der Smagt, 2017;Milletari, Navab, & Ahmadi, 2016) and has recently been shown to have excellent performance in brain tumor segmentation both in an international competition (Isensee, Kickingereder, Wick, Bendszus, & Maier-Hein, 2018) as well as in the context of a largescale multi-institutional study (Kickingereder et al, 2019). Methods S2, Supporting Information, contain an extended description of the architecture, as well as the training and evaluation procedure.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Automated brain extraction of multisequence MRI using artificial neural networks

Isensee

Schell

Pflueger

et al. 2019

Human Brain Mapping

Self Cite

390

253

View full text Add to dashboard Cite

Brain extraction is a critical preprocessing step in the analysis of neuroimaging studies conducted with magnetic resonance imaging (MRI) and influences the accuracy of downstream analyses. The majority of brain extraction algorithms are, however, optimized for processing healthy brains and thus frequently fail in the presence of pathologically altered brain or when applied to heterogeneous MRI datasets. Here we introduce a new, rigorously validated algorithm (termed HD‐BET) relying on artificial neural networks that aim to overcome these limitations. We demonstrate that HD‐BET outperforms six popular, publicly available brain extraction algorithms in several large‐scale neuroimaging datasets, including one from a prospective multicentric trial in neuro‐oncology, yielding state‐of‐the‐art performance with median improvements of +1.16 to +2.50 points for the Dice coefficient and −0.66 to −2.51 mm for the Hausdorff distance. Importantly, the HD‐BET algorithm, which shows robust performance in the presence of pathology or treatment‐induced tissue alterations, is applicable to a broad range of MRI sequence types and is not influenced by variations in MRI hardware and acquisition parameters encountered in both research and clinical practice. For broader accessibility, the HD‐BET prediction algorithm is made freely available (http://www.neuroAI-HD.org) and may become an essential component for robust, automated, high‐throughput processing of MRI neuroimaging data.

show abstract

“…Recently, Isensee et al demonstrated how this relatively simple architecture combined with a robust training scheme achieved state of the art performance on different challenges in segmentation of medical images [11]. A slightly modified version of the architecture was used by Kickingereder et al to not only segment brain lesions, but also to precisely track treatment response by assessing reductions in diameters of the corresponding automated segmentation [12]. The capability of this approach is underlined by the fact that the dataset used in their work not only included glioblastomas but also lower-grade gliomas which typically differ markedly in appearance from their malignant counterparts, which suggests that it may also be useful for segmentation of brain metastases that differ in morphology from both types of glioma.…”

Section: Introductionmentioning

confidence: 99%

Deep convolutional neural networks for automated segmentation of brain metastases trained on clinical data

et al. 2020

View full text Add to dashboard Cite

Introduction: Deep learning-based algorithms have demonstrated enormous performance in segmentation of medical images. We collected a dataset of multiparametric MRI and contour data acquired for use in radiosurgery, to evaluate the performance of deep convolutional neural networks (DCNN) in automatic segmentation of brain metastases (BM). Methods: A conventional U-Net (cU-Net), a modified U-Net (moU-Net) and a U-Net trained only on BM smaller than 0.4 ml (sU-Net) were implemented. Performance was assessed on a separate test set employing sensitivity, specificity, average false positive rate (AFPR), the dice similarity coefficient (DSC), Bland-Altman analysis and the concordance correlation coefficient (CCC). Results: A dataset of 509 patients (1223 BM) was split into a training set (469 pts) and a test set (40 pts). A combination of all trained networks was the most sensitive (0.82) while maintaining a specificity 0.83. The same model achieved a sensitivity of 0.97 and a specificity of 0.94 when considering only lesions larger than 0.06 ml (75% of all lesions). Type of primary cancer had no significant influence on the mean DSC per lesion (p = 0.60). Agreement between manually and automatically assessed tumor volumes as quantified by a CCC of 0.87 (95% CI, 0.77-0.93), was excellent. Conclusion: Using a dataset which properly captured the variation in imaging appearance observed in clinical practice, we were able to conclude that DCNNs reach clinically relevant performance for most lesions. Clinical applicability is currently limited by the size of the target lesion. Further studies should address if small targets are accurately represented in the test data.

show abstract

Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study

Cited by 317 publications

References 70 publications

Heterogeneity of response to immune checkpoint blockade in hypermutated experimental gliomas

Heterogeneity of response to immune checkpoint blockade in hypermutated experimental gliomas

Automated brain extraction of multisequence MRI using artificial neural networks

Deep convolutional neural networks for automated segmentation of brain metastases trained on clinical data

Contact Info

Product

Resources

About